From patchwork Thu Aug 6 09:42:52 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nastya Vicodin X-Patchwork-Id: 1341552 X-Patchwork-Delegate: trini@ti.com Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=lists.denx.de (client-ip=85.214.62.61; helo=phobos.denx.de; envelope-from=u-boot-bounces@lists.denx.de; receiver=) Authentication-Results: ozlabs.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: ozlabs.org; dkim=pass (2048-bit key; unprotected) header.d=gmail.com header.i=@gmail.com header.a=rsa-sha256 header.s=20161025 header.b=NFA2KvR3; dkim-atps=neutral Received: from phobos.denx.de (phobos.denx.de [85.214.62.61]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 4BMkBJ1Zmjz9sTM for ; Thu, 6 Aug 2020 19:45:28 +1000 (AEST) Received: from h2850616.stratoserver.net (localhost [IPv6:::1]) by phobos.denx.de (Postfix) with ESMTP id DB3AB8220C; Thu, 6 Aug 2020 11:43:40 +0200 (CEST) Authentication-Results: phobos.denx.de; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: phobos.denx.de; spf=pass smtp.mailfrom=u-boot-bounces@lists.denx.de Authentication-Results: phobos.denx.de; dkim=pass (2048-bit key; unprotected) header.d=gmail.com header.i=@gmail.com header.b="NFA2KvR3"; dkim-atps=neutral Received: by phobos.denx.de (Postfix, from userid 109) id 9F219821E8; Thu, 6 Aug 2020 11:43:31 +0200 (CEST) X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on phobos.denx.de X-Spam-Level: X-Spam-Status: No, score=-2.0 required=5.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FROM,SPF_HELO_NONE,URIBL_BLOCKED autolearn=ham autolearn_force=no version=3.4.2 Received: from mail-lf1-x134.google.com (mail-lf1-x134.google.com [IPv6:2a00:1450:4864:20::134]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits)) (No client certificate requested) by phobos.denx.de (Postfix) with ESMTPS id D4BFA821E8 for ; Thu, 6 Aug 2020 11:43:19 +0200 (CEST) Authentication-Results: phobos.denx.de; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: phobos.denx.de; spf=pass smtp.mailfrom=vicooodin@gmail.com Received: by mail-lf1-x134.google.com with SMTP id x24so8455125lfe.11 for ; Thu, 06 Aug 2020 02:43:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=+2Vz1A0IoUcExGJY7/kYSFsut/Dvqnbw+ksesebjlRc=; b=NFA2KvR3Q/KI6gXc2si6SWHiM5j9HCFs/MsZaxTR4X80OJsPNkzEysE+kZCUGDkjN6 dJ8UWbKiue2VpvxnG1s9m+8QWvQDvKYs/vv/0kbImNJuNbDPbcX5I0/QuqS/yn+0S27P /k+RxSoMxHg2uj2VBts+JalRHFLTaeKGevoN2UiSB94mNDs3jp5BaVj/lYcjTjXtWnNE D6+oncfEFEAm7wPPHAI3w6fQ/wO6X7eS8nAlNEh55r4gaMOGDB8ZCdLRcQdh9rnUzl2Z Y4LWy0NddId324olxpdLywnYlEZkBIF7UN5H9RE572T6Qhbt8DsiN/lHVdK8Xo8u882T 1SiA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=+2Vz1A0IoUcExGJY7/kYSFsut/Dvqnbw+ksesebjlRc=; b=uX1JG4SwojrvWa2G7qwWo/jsxAI0yJH0fTzhScCKbuaUd8lp3YMFy5fBZKsyO0mNTw hsV/gKQ6ij1lqi/yg/SiRvdPQI7fLK4qkmWfNuhfDl2kLXRxYWXj1/PUvlUtOYGMM1d1 m+QvumZw/AIBTlsm+3nLjQF0xtLG1F4T88GDmYvw8m3KV3RAw5ClvqhRWVCXqE6iAYgv JREv5dYHvkpIETrIZqSmo7aoUBjHRkG0wlX3um6O4CEbZeMSg8MdRLNTii4TV+eoGlXh 3IZ2DN+PnGetbeOzJhQPKzGc5NRNX0JDlAKmDdbRrP8oRXt0HhxmYTuqyBvVL+mZ/1/f apsQ== X-Gm-Message-State: AOAM532DnHES8bd7AQFj50PIk8ShkU/HiiD+tLYpj8v1r1unO+2Y088U pOHja2BUhAblHhGObRHlk/ni1rNnmGqwQQ== X-Google-Smtp-Source: ABdhPJwP/gQd6HpJVhYrws+xn7pIXz3KGzY+F3D2w6la8nUv4txwdpUHdqeMojRdOLshT+XsCtBf+g== X-Received: by 2002:a19:4c57:: with SMTP id z84mr3635332lfa.92.1596706997885; Thu, 06 Aug 2020 02:43:17 -0700 (PDT) Received: from localhost.localdomain (host-176-36-213-80.la.net.ua. [176.36.213.80]) by smtp.gmail.com with ESMTPSA id j13sm2151866ljh.83.2020.08.06.02.43.16 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 06 Aug 2020 02:43:17 -0700 (PDT) From: Anastasiia Lukianenko To: u-boot@lists.denx.de, sjg@chromium.org, ye.li@nxp.com, bmeng.cn@gmail.com, xypron.glpk@gmx.de Cc: julien@xen.org, sstabellini@kernel.org, peng.fan@nxp.com, roman@zededa.com, volodymyr_babchuk@epam.com, andr2000@gmail.com, vicooodin@gmail.com, Andrii Anisov , Anastasiia Lukianenko , Oleksandr Andrushchenko Subject: [RESEND PATCH v2 09/18] lib: sscanf: add sscanf implementation Date: Thu, 6 Aug 2020 12:42:52 +0300 Message-Id: <20200806094301.4999-10-vicooodin@gmail.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20200806094301.4999-1-vicooodin@gmail.com> References: <20200806094301.4999-1-vicooodin@gmail.com> X-BeenThere: u-boot@lists.denx.de X-Mailman-Version: 2.1.34 Precedence: list List-Id: U-Boot discussion List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: u-boot-bounces@lists.denx.de Sender: "U-Boot" X-Virus-Scanned: clamav-milter 0.102.3 at phobos.denx.de X-Virus-Status: Clean From: Andrii Anisov Port sscanf implementation from mini-os and introduce new Kconfig option to enable it: CONFIG_SSCANF. Disable by default. Signed-off-by: Andrii Anisov Signed-off-by: Anastasiia Lukianenko Signed-off-by: Oleksandr Andrushchenko --- Changes since v1: - provide a test in /tests/lib - reduce the code size - add comments - correct code style include/vsprintf.h | 8 + lib/Kconfig | 4 + lib/Makefile | 1 + lib/sscanf.c | 823 +++++++++++++++++++++++++++++++++++++++++++++ test/lib/Makefile | 1 + test/lib/sscanf.c | 174 ++++++++++ 6 files changed, 1011 insertions(+) create mode 100644 lib/sscanf.c create mode 100644 test/lib/sscanf.c diff --git a/include/vsprintf.h b/include/vsprintf.h index d9fb68add0..2290083eba 100644 --- a/include/vsprintf.h +++ b/include/vsprintf.h @@ -234,4 +234,12 @@ char *strmhz(char *buf, unsigned long hz); */ void str_to_upper(const char *in, char *out, size_t len); +/** + * sscanf - Unformat a buffer into a list of arguments + * @buf: input buffer + * @fmt: formatting of buffer + * @...: resulting arguments + */ +int sscanf(const char *buf, const char *fmt, ...); + #endif diff --git a/lib/Kconfig b/lib/Kconfig index 2142bd06e6..efd383ea88 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -80,6 +80,10 @@ config SPL_SPRINTF config TPL_SPRINTF bool +config SSCANF + bool + default n + config STRTO bool default y diff --git a/lib/Makefile b/lib/Makefile index 1dc06c57d5..0cd7bea282 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -123,6 +123,7 @@ else # Main U-Boot always uses the full printf support obj-y += vsprintf.o strto.o obj-$(CONFIG_OID_REGISTRY) += oid_registry.o +obj-$(CONFIG_SSCANF) += sscanf.o endif obj-y += date.o diff --git a/lib/sscanf.c b/lib/sscanf.c new file mode 100644 index 0000000000..d1e2dc272c --- /dev/null +++ b/lib/sscanf.c @@ -0,0 +1,823 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 1990, 1993 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Chris Torek. + * + * Copyright (c) 2011 The FreeBSD Foundation + * All rights reserved. + * Portions of this software were developed by David Chisnall + * under sponsorship from the FreeBSD Foundation. + * + * Author: Juergen Gross + * Date: Jun 2016 + */ + +#if !defined HAVE_LIBC + +#include +#include +#include +#include +#include +#include +#define __DECONST(type, var) ((type)(uintptr_t)(const void *)(var)) + +/** + * struct str_info - Input string parameters + * @neg: negative number or not + * 0 - not negative + * 1 - negative + * @any: set any if any `digits' consumed; make it negative to indicate + * overflow + * @acc: accumulated value + */ +struct str_info { + int neg, any; + u64 acc; +}; + +/** + * str_to_int_convert() - Write string data to structure + * @nptr: pointer to string + * @base: number's base + * @unsign: describes what integer is expected + * 0 - not unsigned + * 1 - unsigned + * + * Ignores `locale' stuff. Assumes that the upper and lower case + * alphabets and digits are each contiguous. + * + * Return: struct str_info *, which contains string data to future process + */ +static struct str_info * +str_to_int_convert(const char **nptr, int base, unsigned int unsign) +{ + const char *s = *nptr; + u64 acc; + unsigned char c; + u64 cutoff; + int neg, any, cutlim; + u64 qbase; + struct str_info *info; + + /* + * Skip white space and pick up leading +/- sign if any. + * If base is 0, allow 0x for hex and 0 for octal, else + * assume decimal; if base is already 16, allow 0x. + */ + info = (struct str_info *)malloc(sizeof(struct str_info)); + if (!info) + return NULL; + + do { + c = *s++; + } while (isspace(c)); + if (c == '-') { + neg = 1; + c = *s++; + } else { + neg = 0; + if (c == '+') + c = *s++; + } + if ((base == 0 || base == 16) && + c == '0' && (*s == 'x' || *s == 'X')) { + c = s[1]; + s += 2; + base = 16; + } + if (base == 0) + base = c == '0' ? 8 : 10; + + /* + * Compute the cutoff value between legal numbers and illegal + * numbers. That is the largest legal value, divided by the + * base. An input number that is greater than this value, if + * followed by a legal input character, is too big. One that + * is equal to this value may be valid or not; the limit + * between valid and invalid numbers is then based on the last + * digit. For instance, if the range for quads is + * [-9223372036854775808..9223372036854775807] and the input base + * is 10, cutoff will be set to 922337203685477580 and cutlim to + * either 7 (neg==0) or 8 (neg==1), meaning that if we have + * accumulated a value > 922337203685477580, or equal but the + * next digit is > 7 (or 8), the number is too big, and we will + * return a range error. + * + * Set any if any `digits' consumed; make it negative to indicate + * overflow. + */ + qbase = (unsigned int)base; + + if (!unsign) { + cutoff = neg ? (u64)-(LLONG_MIN + LLONG_MAX) + LLONG_MAX : LLONG_MAX; + cutlim = cutoff % qbase; + cutoff /= qbase; + } else { + cutoff = (u64)ULLONG_MAX / qbase; + cutlim = (u64)ULLONG_MAX % qbase; + } + + for (acc = 0, any = 0;; c = *s++) { + if (!isascii(c)) + break; + if (isdigit(c)) + c -= '0'; + else if (isalpha(c)) + c -= isupper(c) ? 'A' - 10 : 'a' - 10; + else + break; + if (c >= base) + break; + if (any < 0 || acc > cutoff || (acc == cutoff && c > cutlim)) { + any = -1; + } else { + any = 1; + acc *= qbase; + acc += c; + } + } + + info->any = any; + info->neg = neg; + info->acc = acc; + + *nptr = s; + + return info; +} + +/** + * strtoq() - Convert a string to a quad integer + * @nptr: pointer to string + * @endptr: pointer to number's end in the string + * @base: number's base + * + * Return: s64 quad integer number converted from input string + */ +static s64 +strtoq(const char *nptr, char **endptr, int base) +{ + const char *s = nptr; + u64 acc; + int unsign = 0; + struct str_info *info; + + info = str_to_int_convert(&s, base, unsign); + if (!info) + return -1; + + acc = info->acc; + + if (info->any < 0) + acc = info->neg ? LLONG_MIN : LLONG_MAX; + else if (info->neg) + acc = -acc; + if (endptr != 0) + *endptr = __DECONST(char *, info->any ? s - 1 : nptr); + + free(info); + + return acc; +} + +/** + * strtouq() - Convert a string to an unsigned quad integer + * @nptr: pointer to string + * @endptr: pointer to number's end in the string + * @base: number's base + * + * Return: s64 unsigned quad integer number converted from + * input string + */ +u64 +strtouq(const char *nptr, char **endptr, int base) +{ + const char *s = nptr; + u64 acc; + int unsign = 1; + struct str_info *info; + + info = str_to_int_convert(&s, base, unsign); + if (!info) + return -1; + + acc = info->acc; + + if (info->any < 0) + acc = ULLONG_MAX; + else if (info->neg) + acc = -acc; + if (endptr != 0) + *endptr = __DECONST(char *, info->any ? s - 1 : nptr); + + free(info); + + return acc; +} + +/** + * __sccl() - Fill in the given table from the scanset at the given format + * (just after `[') + * @tab: table to fill in + * @fmt: format of buffer + * + * The table has a 1 wherever characters should be considered part of the + * scanset. + * + * Return: pointer to the character past the closing `]' + */ +static const u_char * +__sccl(char *tab, const u_char *fmt) +{ + int c, n, v; + + /* first `clear' the whole table */ + c = *fmt++; /* first char hat => negated scanset */ + if (c == '^') { + v = 1; /* default => accept */ + c = *fmt++; /* get new first char */ + } else { + v = 0; /* default => reject */ + } + + /* XXX: Will not work if sizeof(tab*) > sizeof(char) */ + for (n = 0; n < 256; n++) + tab[n] = v; /* memset(tab, v, 256) */ + + if (c == 0) + return (fmt - 1);/* format ended before closing ] */ + + /* + * Now set the entries corresponding to the actual scanset + * to the opposite of the above. + * + * The first character may be ']' (or '-') without being special; + * the last character may be '-'. + */ + v = 1 - v; + for (;;) { + tab[c] = v; /* take character c */ +doswitch: + n = *fmt++; /* and examine the next */ + switch (n) { + case 0: /* format ended too soon */ + return (fmt - 1); + + case '-': + /* + * A scanset of the form + * [01+-] + * is defined as `the digit 0, the digit 1, + * the character +, the character -', but + * the effect of a scanset such as + * [a-zA-Z0-9] + * is implementation defined. The V7 Unix + * scanf treats `a-z' as `the letters a through + * z', but treats `a-a' as `the letter a, the + * character -, and the letter a'. + * + * For compatibility, the `-' is not considerd + * to define a range if the character following + * it is either a close bracket (required by ANSI) + * or is not numerically greater than the character + * we just stored in the table (c). + */ + n = *fmt; + if (n == ']' || n < c) { + c = '-'; + break; /* resume the for(;;) */ + } + fmt++; + /* fill in the range */ + do { + tab[++c] = v; + } while (c < n); + c = n; + /* + * Alas, the V7 Unix scanf also treats formats + * such as [a-c-e] as `the letters a through e'. + * This too is permitted by the standard.... + */ + goto doswitch; + break; + + case ']': /* end of scanset */ + return (fmt); + + default: /* just another character */ + c = n; + break; + } + } + /* NOTREACHED */ +} + +/** + * vsscanf - Unformat a buffer into a list of arguments + * @buf: input buffer + * @fmt: format of buffer + * @args: arguments + */ +#define BUF 32 /* Maximum length of numeric string. */ + +/* + * Flags used during conversion. + */ +#define LONG 0x01 /* l: long or double */ +#define SHORT 0x04 /* h: short */ +#define SUPPRESS 0x08 /* suppress assignment */ +#define POINTER 0x10 /* weird %p pointer (`fake hex') */ +#define NOSKIP 0x20 /* do not skip blanks */ +#define QUAD 0x400 +#define SHORTSHORT 0x4000 /** hh: char */ + +/* + * The following are used in numeric conversions only: + * SIGNOK, NDIGITS, DPTOK, and EXPOK are for floating point; + * SIGNOK, NDIGITS, PFXOK, and NZDIGITS are for integral. + */ +#define SIGNOK 0x40 /* +/- is (still) legal */ +#define NDIGITS 0x80 /* no digits detected */ + +#define DPTOK 0x100 /* (float) decimal point is still legal */ +#define EXPOK 0x200 /* (float) exponent (e+3, etc) still legal */ + +#define PFXOK 0x100 /* 0x prefix is (still) legal */ +#define NZDIGITS 0x200 /* no zero digits detected */ + +/* + * Conversion types. + */ +#define CT_CHAR 0 /* %c conversion */ +#define CT_CCL 1 /* %[...] conversion */ +#define CT_STRING 2 /* %s conversion */ +#define CT_INT 3 /* integer, i.e., strtoq or strtouq */ +typedef u64 (*ccfntype)(const char *, char **, int); + +int +vsscanf(const char *inp, char const *fmt0, va_list ap) +{ + int inr; + const u_char *fmt = (const u_char *)fmt0; + int c; /* character from format, or conversion */ + size_t width; /* field width, or 0 */ + char *p; /* points into all kinds of strings */ + int n; /* handy integer */ + int flags; /* flags as defined above */ + char *p0; /* saves original value of p when necessary */ + int nassigned; /* number of fields assigned */ + int nconversions; /* number of conversions */ + int nread; /* number of characters consumed from fp */ + int base; /* base argument to strtoq/strtouq */ + ccfntype ccfn; /* conversion function (strtoq/strtouq) */ + char ccltab[256]; /* character class table for %[...] */ + char buf[BUF]; /* buffer for numeric conversions */ + + /* `basefix' is used to avoid `if' tests in the integer scanner */ + static short basefix[17] = { 10, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, + 12, 13, 14, 15, 16 }; + + inr = strlen(inp); + + nassigned = 0; + nconversions = 0; + nread = 0; + base = 0; /* XXX just to keep gcc happy */ + ccfn = NULL; /* XXX just to keep gcc happy */ + for (;;) { + c = *fmt++; + if (c == 0) + return (nassigned); + if (isspace(c)) { + while (inr > 0 && isspace(*inp)) + nread++, inr--, inp++; + continue; + } + if (c != '%') + goto literal; + width = 0; + flags = 0; + /* + * switch on the format. continue if done; + * break once format type is derived. + */ +again: c = *fmt++; + switch (c) { + case '%': +literal: + if (inr <= 0) + goto input_failure; + if (*inp != c) + goto match_failure; + inr--, inp++; + nread++; + continue; + + case '*': + flags |= SUPPRESS; + goto again; + case 'l': + if (flags & LONG) { + flags &= ~LONG; + flags |= QUAD; + } else { + flags |= LONG; + } + goto again; + case 'q': + flags |= QUAD; + goto again; + case 'h': + if (flags & SHORT) { + flags &= ~SHORT; + flags |= SHORTSHORT; + } else { + flags |= SHORT; + } + goto again; + + case '0': case '1': case '2': case '3': case '4': + case '5': case '6': case '7': case '8': case '9': + width = width * 10 + c - '0'; + goto again; + + /* + * Conversions. + * + */ + case 'd': + c = CT_INT; + ccfn = (ccfntype)strtoq; + base = 10; + break; + + case 'i': + c = CT_INT; + ccfn = (ccfntype)strtoq; + base = 0; + break; + + case 'o': + c = CT_INT; + ccfn = strtouq; + base = 8; + break; + + case 'u': + c = CT_INT; + ccfn = strtouq; + base = 10; + break; + + case 'x': + flags |= PFXOK; /* enable 0x prefixing */ + c = CT_INT; + ccfn = strtouq; + base = 16; + break; + + case 's': + c = CT_STRING; + break; + + case '[': + fmt = __sccl(ccltab, fmt); + flags |= NOSKIP; + c = CT_CCL; + break; + + case 'c': + flags |= NOSKIP; + c = CT_CHAR; + break; + + case 'p': /* pointer format is like hex */ + flags |= POINTER | PFXOK; + c = CT_INT; + ccfn = strtouq; + base = 16; + break; + + case 'n': + nconversions++; + if (flags & SUPPRESS) /* ??? */ + continue; + if (flags & SHORTSHORT) + *va_arg(ap, char *) = nread; + else if (flags & SHORT) + *va_arg(ap, short *) = nread; + else if (flags & LONG) + *va_arg(ap, long *) = nread; + else if (flags & QUAD) + *va_arg(ap, s64 *) = nread; + else + *va_arg(ap, int *) = nread; + continue; + } + + /* + * We have a conversion that requires input. + */ + if (inr <= 0) + goto input_failure; + + /* + * Consume leading white space, except for formats + * that suppress this. + */ + if ((flags & NOSKIP) == 0) { + while (isspace(*inp)) { + nread++; + if (--inr > 0) + inp++; + else + goto input_failure; + } + /* + * Note that there is at least one character in + * the buffer, so conversions that do not set NOSKIP + * can no longer result in an input failure. + */ + } + + /* + * Do the conversion. + */ + switch (c) { + case CT_CHAR: + /* scan arbitrary characters (sets NOSKIP) */ + if (width == 0) + width = 1; + if (flags & SUPPRESS) { + size_t sum = 0; + + if ((n = inr) < width) { + sum += n; + width -= n; + inp += n; + if (sum == 0) + goto input_failure; + } else { + sum += width; + inr -= width; + inp += width; + } + nread += sum; + } else { + memcpy(va_arg(ap, char *), inp, width); + inr -= width; + inp += width; + nread += width; + nassigned++; + } + nconversions++; + break; + + case CT_CCL: + /* scan a (nonempty) character class (sets NOSKIP) */ + if (width == 0) + width = (size_t)~0; /* `infinity' */ + /* take only those things in the class */ + if (flags & SUPPRESS) { + n = 0; + while (ccltab[(unsigned char)*inp]) { + n++, inr--, inp++; + if (--width == 0) + break; + if (inr <= 0) { + if (n == 0) + goto input_failure; + break; + } + } + if (n == 0) + goto match_failure; + } else { + p = va_arg(ap, char *); + p0 = p; + while (ccltab[(unsigned char)*inp]) { + inr--; + *p++ = *inp++; + if (--width == 0) + break; + if (inr <= 0) { + if (p == p0) + goto input_failure; + break; + } + } + n = p - p0; + if (n == 0) + goto match_failure; + *p = 0; + nassigned++; + } + nread += n; + nconversions++; + break; + + case CT_STRING: + /* like CCL, but zero-length string OK, & no NOSKIP */ + if (width == 0) + width = (size_t)~0; + if (flags & SUPPRESS) { + n = 0; + while (!isspace(*inp)) { + n++, inr--, inp++; + if (--width == 0) + break; + if (inr <= 0) + break; + } + nread += n; + } else { + p = va_arg(ap, char *); + p0 = p; + while (!isspace(*inp)) { + inr--; + *p++ = *inp++; + if (--width == 0) + break; + if (inr <= 0) + break; + } + *p = 0; + nread += p - p0; + nassigned++; + } + nconversions++; + continue; + + case CT_INT: + /* scan an integer as if by strtoq/strtouq */ +#ifdef hardway + if (width == 0 || width > sizeof(buf) - 1) + width = sizeof(buf) - 1; +#else + /* size_t is unsigned, hence this optimisation */ + if (--width > sizeof(buf) - 2) + width = sizeof(buf) - 2; + width++; +#endif + flags |= SIGNOK | NDIGITS | NZDIGITS; + for (p = buf; width; width--) { + c = *inp; + /* + * Switch on the character; `goto ok' + * if we accept it as a part of number. + */ + switch (c) { + /* + * The digit 0 is always legal, but is + * special. For %i conversions, if no + * digits (zero or nonzero) have been + * scanned (only signs), we will have + * base==0. In that case, we should set + * it to 8 and enable 0x prefixing. + * Also, if we have not scanned zero digits + * before this, do not turn off prefixing + * (someone else will turn it off if we + * have scanned any nonzero digits). + */ + case '0': + if (base == 0) { + base = 8; + flags |= PFXOK; + } + if (flags & NZDIGITS) + flags &= ~(SIGNOK | NZDIGITS | NDIGITS); + else + flags &= ~(SIGNOK | PFXOK | NDIGITS); + goto ok; + + /* 1 through 7 always legal */ + case '1': case '2': case '3': + case '4': case '5': case '6': case '7': + base = basefix[base]; + flags &= ~(SIGNOK | PFXOK | NDIGITS); + goto ok; + + /* digits 8 and 9 ok iff decimal or hex */ + case '8': case '9': + base = basefix[base]; + if (base <= 8) + break; /* not legal here */ + flags &= ~(SIGNOK | PFXOK | NDIGITS); + goto ok; + + /* letters ok iff hex */ + case 'A': case 'B': case 'C': + case 'D': case 'E': case 'F': + case 'a': case 'b': case 'c': + case 'd': case 'e': case 'f': + /* no need to fix base here */ + if (base <= 10) + break; /* not legal here */ + flags &= ~(SIGNOK | PFXOK | NDIGITS); + goto ok; + + /* sign ok only as first character */ + case '+': case '-': + if (flags & SIGNOK) { + flags &= ~SIGNOK; + goto ok; + } + break; + + /* x ok iff flag still set & 2nd char */ + case 'x': case 'X': + if (flags & PFXOK && p == buf + 1) { + base = 16; /* if %i */ + flags &= ~PFXOK; + goto ok; + } + break; + } + + /* + * If we got here, c is not a legal character + * for a number. Stop accumulating digits. + */ + break; +ok: + /* + * c is legal: store it and look at the next. + */ + *p++ = c; + if (--inr > 0) + inp++; + else + break; /* end of input */ + } + /* + * If we had only a sign, it is no good; push + * back the sign. If the number ends in `x', + * it was [sign] '' 'x', so push back the x + * and treat it as [sign] ''. + */ + if (flags & NDIGITS) { + if (p > buf) { + inp--; + inr++; + } + goto match_failure; + } + c = ((u_char *)p)[-1]; + if (c == 'x' || c == 'X') { + --p; + inp--; + inr++; + } + if ((flags & SUPPRESS) == 0) { + u64 res; + + *p = 0; + res = (*ccfn)(buf, (char **)NULL, base); + if (flags & POINTER) + *va_arg(ap, void **) = + (void *)(uintptr_t)res; + else if (flags & SHORTSHORT) + *va_arg(ap, char *) = res; + else if (flags & SHORT) + *va_arg(ap, short *) = res; + else if (flags & LONG) + *va_arg(ap, long *) = res; + else if (flags & QUAD) + *va_arg(ap, s64 *) = res; + else + *va_arg(ap, int *) = res; + nassigned++; + } + nread += p - buf; + nconversions++; + break; + } + } +input_failure: + return (nconversions != 0 ? nassigned : -1); +match_failure: + return (nassigned); +} + +/** + * sscanf - Unformat a buffer into a list of arguments + * @buf: input buffer + * @fmt: formatting of buffer + * @...: resulting arguments + */ +int sscanf(const char *buf, const char *fmt, ...) +{ + va_list args; + int i; + + va_start(args, fmt); + i = vsscanf(buf, fmt, args); + va_end(args); + return i; +} + +#endif diff --git a/test/lib/Makefile b/test/lib/Makefile index 6ccc2c41bc..b6a0a208c5 100644 --- a/test/lib/Makefile +++ b/test/lib/Makefile @@ -6,6 +6,7 @@ obj-y += cmd_ut_lib.o obj-$(CONFIG_EFI_SECURE_BOOT) += efi_image_region.o obj-y += hexdump.o obj-y += lmb.o +obj-y += sscanf.o obj-y += string.o obj-$(CONFIG_ERRNO_STR) += test_errno_str.o obj-$(CONFIG_UT_LIB_ASN1) += asn1.o diff --git a/test/lib/sscanf.c b/test/lib/sscanf.c new file mode 100644 index 0000000000..772e4b9204 --- /dev/null +++ b/test/lib/sscanf.c @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2002, Uwe Bonnes + * Copyright (c) 2001-2004, Roger Dingledine. + * Copyright (c) 2004-2006, Roger Dingledine, Nick Mathewson. + * Copyright (c) 2007-2016, The Tor Project, Inc. + * Copyright (c) 2020, EPAM Systems Inc. + * + * Unit tests for sscanf() function + */ + +#include +#include +#include +#include +#include +#include + +#define EOF -1 + +/** + * lib_sscanf() - unit test for sscanf() + * @uts: unit test state + * + * Test sscanf() with varied parameters in different combinations passed + * as arguments. + * + * Return: 0 - success + * 1 - failure + */ +static int lib_sscanf(struct unit_test_state *uts) +{ + char buffer[100], buffer1[100]; + int result, ret; + static const char pname[] = " Hello World!\n"; + int hour = 21, min = 59, sec = 20; + int number, number_so_far; + unsigned int u1, u2, u3; + char s1[20], s2[10], s3[10], ch; + int r, int1, int2; + long lng1; + + /* check EOF */ + strcpy(buffer, ""); + ret = sscanf(buffer, "%d", &result); + ut_asserteq(ret, EOF); + + /* check %x */ + strcpy(buffer, "0x519"); + ut_asserteq(sscanf(buffer, "%x", &result), 1); + ut_asserteq(result, 0x519); + + strcpy(buffer, "0x51a"); + ut_asserteq(sscanf(buffer, "%x", &result), 1); + ut_asserteq(result, 0x51a); + + strcpy(buffer, "0x51g"); + ut_asserteq(sscanf(buffer, "%x", &result), 1); + ut_asserteq(result, 0x51); + + /* check strings */ + ret = sprintf(buffer, " %s", pname); + ret = sscanf(buffer, "%*c%[^\n]", buffer1); + ut_asserteq(ret, 1); + ut_asserteq(strncmp(pname, buffer1, strlen(buffer1)), 0); + + /* check digits */ + ret = sprintf(buffer, "%d:%d:%d", hour, min, sec); + ret = sscanf(buffer, "%d%n", &number, &number_so_far); + ut_asserteq(ret, 1); + ut_asserteq(number, hour); + ut_asserteq(number_so_far, 2); + + ret = sscanf(buffer + 2, "%*c%n", &number_so_far); + ut_asserteq(ret, 0); + ut_asserteq(number_so_far, 1); + + /* Check %i */ + strcpy(buffer, "123"); + ret = sscanf(buffer, "%i", &result); + ut_asserteq(ret, 1); + ut_asserteq(result, 123); + ret = sscanf(buffer, "%d", &result); + ut_asserteq(ret, 1); + ut_asserteq(result, 123); + + ut_asserteq(0, sscanf("hello world", "hello world")); + ut_asserteq(0, sscanf("hello world", "good bye")); + /* Excess data */ + ut_asserteq(0, sscanf("hello 3", "%u", &u1)); /* have to match the start */ + ut_asserteq(1, sscanf("3 hello", "%u", &u1)); /* but trailing is alright */ + + /* Numbers (ie. %u) */ + ut_asserteq(0, sscanf("hello world 3", "hello worlb %u", &u1)); /* d vs b */ + ut_asserteq(1, sscanf("12345", "%u", &u1)); + ut_asserteq(12345u, u1); + ut_asserteq(1, sscanf("0", "%u", &u1)); + ut_asserteq(0u, u1); + ut_asserteq(1, sscanf("0000", "%u", &u2)); + ut_asserteq(0u, u2); + ut_asserteq(0, sscanf("A", "%u", &u1)); /* bogus number */ + + /* Numbers with size (eg. %2u) */ + ut_asserteq(2, sscanf("123456", "%2u%u", &u1, &u2)); + ut_asserteq(12u, u1); + ut_asserteq(3456u, u2); + ut_asserteq(1, sscanf("123456", "%8u", &u1)); + ut_asserteq(123456u, u1); + ut_asserteq(1, sscanf("123457 ", "%8u", &u1)); + ut_asserteq(123457u, u1); + ut_asserteq(3, sscanf("!12:3:456", "!%2u:%2u:%3u", &u1, &u2, &u3)); + ut_asserteq(12u, u1); + ut_asserteq(3u, u2); + ut_asserteq(456u, u3); + ut_asserteq(3, sscanf("67:8:099", "%2u:%2u:%3u", &u1, &u2, &u3)); /* 0s */ + ut_asserteq(67u, u1); + ut_asserteq(8u, u2); + ut_asserteq(99u, u3); + /* Arbitrary amounts of 0-padding are okay */ + ut_asserteq(3, sscanf("12:03:000000000000000099", "%2u:%2u:%u", &u1, &u2, &u3)); + ut_asserteq(12u, u1); + ut_asserteq(3u, u2); + ut_asserteq(99u, u3); + + /* Hex (ie. %x) */ + ut_asserteq(3, sscanf("1234 02aBcdEf ff", "%x %x %x", &u1, &u2, &u3)); + ut_asserteq(0x1234, u1); + ut_asserteq(0x2ABCDEF, u2); + ut_asserteq(0xFF, u3); + /* Width works on %x */ + ut_asserteq(3, sscanf("f00dcafe444", "%4x%4x%u", &u1, &u2, &u3)); + ut_asserteq(0xf00d, u1); + ut_asserteq(0xcafe, u2); + ut_asserteq(444, u3); + + /* Literal '%' (ie. '%%') */ + ut_asserteq(1, sscanf("99% fresh", "%3u%% fresh", &u1)); + ut_asserteq(99, u1); + ut_asserteq(0, sscanf("99 fresh", "%% %3u %s", &u1, s1)); + ut_asserteq(1, sscanf("99 fresh", "%3u%% %s", &u1, s1)); + ut_asserteq(2, sscanf("99 fresh", "%3u %5s %%", &u1, s1)); + ut_asserteq(99, u1); + ut_asserteq_str(s1, "fresh"); + ut_asserteq(1, sscanf("% boo", "%% %3s", s1)); + ut_asserteq_str("boo", s1); + + /* Strings (ie. %s) */ + ut_asserteq(2, sscanf("hello", "%3s%7s", s1, s2)); + ut_asserteq_str(s1, "hel"); + ut_asserteq_str(s2, "lo"); + ut_asserteq(2, sscanf("WD40", "%2s%u", s3, &u1)); /* %s%u */ + ut_asserteq_str(s3, "WD"); + ut_asserteq(40, u1); + ut_asserteq(2, sscanf("WD40", "%3s%u", s3, &u1)); /* %s%u */ + ut_asserteq_str(s3, "WD4"); + ut_asserteq(0, u1); + ut_asserteq(2, sscanf("76trombones", "%6u%9s", &u1, s1)); /* %u%s */ + ut_asserteq(76, u1); + ut_asserteq_str(s1, "trombones"); + + ut_asserteq(3, sscanf("1.2.3", "%u.%u.%u%c", &u1, &u2, &u3, &ch)); + ut_asserteq(4, sscanf("1.2.3 foobar", "%u.%u.%u%c", &u1, &u2, &u3, &ch)); + ut_asserteq(' ', ch); + + r = sscanf("12345 -67890 -1", "%d %ld %d", &int1, &lng1, &int2); + ut_asserteq(r, 3); + ut_asserteq(int1, 12345); + ut_asserteq(lng1, -67890); + ut_asserteq(int2, -1); + + return 0; +} + +LIB_TEST(lib_sscanf, 0);